CN109801072B - Private key generation method and system of block chain electronic wallet based on facial features - Google Patents
Private key generation method and system of block chain electronic wallet based on facial features Download PDFInfo
- Publication number
- CN109801072B CN109801072B CN201910066500.8A CN201910066500A CN109801072B CN 109801072 B CN109801072 B CN 109801072B CN 201910066500 A CN201910066500 A CN 201910066500A CN 109801072 B CN109801072 B CN 109801072B
- Authority
- CN
- China
- Prior art keywords
- vector
- user
- private key
- matrix
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The application provides a private key generation method and a private key generation system of a block chain electronic wallet based on facial features, wherein the private key generation method comprises the following steps: establishing a characteristic face recognition library; extracting characteristic face principal vectors from gray level images corresponding to a plurality of face images in a characteristic face recognition library; acquiring an image of facial features of a user; establishing an association degree vector of the facial feature image of the user according to the facial feature image of the user and the feature face main vector; and generating a private key corresponding to the facial feature information of the user according to the relevance vector. The private key is generated based on the strong authentication facial feature information, the relevance between the private key and the facial feature information of the user is strong, the safety of the private key can be improved, and the private key cannot be easily calculated out to obtain a specific value. In addition, the private key no longer needs to be stored, and the risks of being stolen and illegally used can be avoided. The private key can be reproduced according to the facial feature information of the user when the private key is lost or the storage device is forgotten to be carried.
Description
Technical Field
The application belongs to the technical field of information security, and particularly relates to a private key generation method and system for a block chain electronic wallet based on facial features.
Background
In the block chain-based electronic wallet technology, the asymmetric encryption technology has a crucial influence on the security and reliability of the transaction. In the asymmetric encryption technology, a public key and a private key are generated through an encryption algorithm, the public key is used for encryption, and the private key is used for decryption. Typically, the public and private keys of the e-wallet user are generated at registration time and remain unchanged. The private key is held by the user and cannot be disclosed to other people, otherwise the security of the transaction is greatly threatened.
In the prior art, a public key and a private key are randomly generated based on the condition of an encryption algorithm and are stored in a certain database or equipment. Although the storage environment for the private key may be secure and confidential, the risk of theft of the private key is still not completely avoided. If the private key is stored in a centralized database of a certain operator, there may also be a risk that the operator violates the viewing of the user's private key. The greatest advantage of the personal electronic wallet based on the blockchain is a decentralized storage mode, and if the private key is stored in a centralized manner by an operator, the characteristics and advantages of the blockchain cannot be fully exerted.
In the actual application process, the operator acquires the facial features of the user and compares the facial features with facial feature data recorded in a database or equipment to generate a verification result. And directly associating the face information of the user with the corresponding private key after the user passes the authentication. However, the private key is often weakly associated with the facial feature information of the user, and once the private key is lost or forgotten to carry the storage terminal, the private key cannot be reproduced, and only the private key can be regenerated. In addition, when the user steals the mobile phone, the tablet computer and other devices storing the private key, the private key of the user is at risk of being stolen.
Therefore, no matter the client side stores or the operator stores, the private key cannot effectively avoid the risk of being stolen, and the threat on transaction safety cannot be avoided.
Disclosure of Invention
To overcome, at least in part, the problems in the related art, the present application provides a private key generation method and system for a blockchain e-wallet based on facial features.
According to a first aspect of embodiments of the present application, there is provided a private key generation method for a blockchain electronic wallet based on facial features, comprising the steps of:
establishing a characteristic face recognition library;
extracting characteristic face principal vectors from gray level images corresponding to a plurality of face images in a characteristic face recognition library;
acquiring an image of facial features of a user;
establishing an association degree vector of the facial feature image of the user according to the facial feature image of the user and the feature face main vector;
and generating a private key corresponding to the facial feature information of the user according to the relevance vector.
In the private key generation method, the specific process of establishing the characteristic face recognition library in the step is as follows:
randomly collecting U different face images;
for each face image, correspondingly converting the face image into a gray image, wherein the size of the gray image is m × n pixels;
converting a matrix formed by m × n pixels of the gray-scale image into m × n dimensional row vectors;
and arranging the row vectors corresponding to the U different face images into a matrix A, wherein the matrix A is a matrix with U rows and m × n columns.
In the private key generation method, the specific process of extracting the feature face principal vector in the step is as follows:
performing decentralized processing on each row of elements in the matrix A respectively;
establishing a covariance matrix for the matrix subjected to the decentralized processing;
calculating all eigenvalues of the covariance matrix and eigenvectors corresponding to the eigenvalues;
sorting the m-n characteristic values, selecting a plurality of largest characteristic values, forming a new characteristic array according to the sequence from large to small, and forming a new characteristic vector matrix by the characteristic vectors corresponding to the characteristic values in the characteristic array;
and calculating the projection of the matrix subjected to the centralization treatment on the characteristic vector matrix to obtain the characteristic face main vector.
In the above private key generating method, the specific process of performing decentralized processing on each row of elements in the matrix a in the step is as follows:
calculating the average value of each column of elements;
wherein k is 1,2,3, …, U, j is 1,2,3, …, m × n; mu.sjRepresents the average value of j column element in matrix A;
and subtracting the average value of the column of each element in the matrix A to obtain the matrix after the decentralization treatment.
In the private key generation method, the specific process of establishing the relevance vector of the facial feature image of the user according to the facial feature image and the feature face principal vector of the user comprises the following steps:
converting a facial feature image of a user into a grayscale image, wherein the grayscale image has m × n pixels;
converting a matrix formed by m × n pixels of the gray-scale image into m × n dimensional row vectors z;
calculating the projection of the m x n dimensional row vector z on the feature vector matrix P to obtain the feature face main vector y of the user:
y＝z×P，
in the formula, x represents matrix multiplication, and the eigenface main vector y of the user represents a row vector of 1 row and h columns;
calculating an association degree vector x of the facial feature image of the user:
x＝(DDT)-1DyT，
in the formula, T represents a transpose of a matrix.
In the private key generation method, the specific process of generating the private key corresponding to the facial feature information of the user according to the relevance vector comprises the following steps:
for each element in the relevance vector x, its rounded integer e is calculatedg：
eg＝round(xg·10τ),g＝1,2,…,U，
In the formula, round represents rounding according to a rounding rule; τ represents a tunable parameter, which is a non-negative integer;
and arranging and generating a private key corresponding to the facial feature information of the user according to a preset sequence.
Before the step of collecting the image of the facial features of the user, the private key generating method further comprises the following steps: the user himself/herself is confirmed by a biometric authentication method.
According to a second aspect of embodiments of the present application, there is provided a face feature-based private key generation system for a blockchain electronic wallet, comprising:
the recognition base establishing module is used for establishing a characteristic face recognition base according to a plurality of randomly collected different face images;
the extraction module is used for extracting a characteristic face principal vector from a gray level image corresponding to a face image in a characteristic face recognition library;
and the image acquisition module is used for acquiring facial feature images of the user.
The system comprises an association degree vector establishing module, a face feature image generating module and a face feature vector establishing module, wherein the association degree vector establishing module is used for establishing an association degree vector of a face feature image of a user according to the face feature image and a feature face main vector of the user;
and the generating module is used for generating a private key corresponding to the facial feature information of the user according to the relevance vector.
In the above private key generating system, the association degree vector establishing module includes:
a matrix transformation module for transforming a matrix formed by m × n pixels of the gray-scale image transformed from the facial feature image of the user into m × n dimensional row vectors;
and the relevance vector calculation module is used for calculating the relevance vector of the user face feature image by utilizing the projection of the m-n dimensional row vector on the feature vector matrix and the feature face main vector.
According to a third aspect of embodiments of the present application, there is provided a private key generation apparatus for a blockchain wallet based on facial features, comprising:
a processor for processing the received data, wherein the processor is used for processing the received data,
the processor is capable of invoking intelligent contracts from a blockchain,
the intelligent contract comprises a computer program that,
the computer program, when running on the processor, performs the steps of:
establishing a characteristic face recognition library;
extracting characteristic face principal vectors from gray level images corresponding to a plurality of face images in a characteristic face recognition library;
acquiring an image of facial features of a user;
establishing an association degree vector of the facial feature image of the user according to the facial feature image of the user and the feature face main vector;
and generating a private key corresponding to the facial feature information of the user according to the relevance vector.
According to a fourth aspect of embodiments of the present application, there is provided a blockchain-based personal electronic wallet comprising a private key generated by any one of the private key generation methods described above, the private key generation method being stored as a smart contract on the blockchain.
According to the above embodiments of the present application, at least the following advantages are obtained: the private key generation method generates the private key based on the strong authentication biological characteristic information, the private key is strong in correlation with the facial characteristic information of the user, the safety of the private key can be improved, and the private key cannot be easily deduced to be a specific value. The private key generated by the method is used in the personal electronic wallet based on the block chain, the private key does not need to be stored any more, and risks of being stolen and being illegally used can be avoided. The present application can enhance the decentralized nature of blockchain personal electronic wallets. The storage medium is not needed, and the private key can be reproduced according to the facial feature information of the user when the private key is lost or the storage device is forgotten to be carried.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the scope of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of the specification of the application, illustrate embodiments of the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a flowchart of a private key generation method for a blockchain wallet based on facial features according to an embodiment of the present disclosure.
Fig. 2 is a schematic structural diagram of a private key generation system of a blockchain wallet based on facial features according to an embodiment of the present invention.
Fig. 3 is a schematic diagram illustrating an application state of a personal electronic wallet based on a blockchain according to an embodiment of the present invention.
Detailed Description
For the purpose of promoting a clear understanding of the objects, aspects and advantages of the embodiments of the present application, reference will now be made to the accompanying drawings and detailed description, wherein like reference numerals refer to like elements throughout.
The illustrative embodiments and descriptions of the present application are provided to explain the present application and not to limit the present application. Additionally, the same or similar numbered elements/components used in the drawings and the embodiments are used to represent the same or similar parts.
As used herein, "first," "second," …, etc., are not specifically intended to mean in a sequential or chronological order, nor are they intended to limit the application, but merely to distinguish between elements or operations described in the same technical language.
With respect to directional terminology used herein, for example: up, down, left, right, front or rear, etc., are simply directions with reference to the drawings. Accordingly, the directional terminology used is intended to be illustrative and is not intended to be limiting of the present teachings.
As used herein, the terms "comprising," "including," "having," "containing," and the like are open-ended terms that mean including, but not limited to.
As used herein, "and/or" includes any and all combinations of the described items.
References to "plurality" herein include "two" and "more than two"; reference to "multiple sets" herein includes "two sets" and "more than two sets".
As used herein, the terms "substantially", "about" and the like are used to modify any slight variation in quantity or error that does not alter the nature of the variation. In general, the range of slight variations or errors that such terms modify may be 20% in some embodiments, 10% in some embodiments, 5% in some embodiments, or other values. It should be understood by those skilled in the art that the aforementioned values can be adjusted according to actual needs, and are not limited thereto.
Certain words used to describe the present application are discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art in describing the present application.
Example one
Fig. 1 is a flowchart of a private key generation method for a blockchain wallet based on facial features according to an embodiment of the present application. As shown in fig. 1, the private key generation method of the blockchain electronic wallet based on the facial features includes the following steps:
s1, establishing a characteristic face recognition library, wherein the specific process is as follows:
and S11, randomly collecting U different face images.
And S12, correspondingly converting each face image into a gray image with the size of m × n pixels. The value of U can be set according to the actual application scene; m denotes the number of rows of image pixels and n denotes the number of columns of image pixels.
S13, converting the matrix of m × n pixels of the gray-scale image into m × n-dimensional row vector a.
S14, arranging the row vectors a corresponding to U different face images into a matrix A, namely the matrix A is a matrix of U rows m x n columns; the matrix a may be of the form:
in general, an image having a size of, for example, 100 × 100, where m × n is larger than U, has 10000 pixels in total, and the amount of data in the feature face recognition library, i.e., U, is several tens to several hundreds.
S2, extracting the characteristic face principal vectors from the gray level images corresponding to the U face images in the characteristic face recognition library, wherein the specific process is as follows:
s21, performing decentralized processing on each row of elements in the matrix A respectively, wherein the process is as follows:
the average value of each column element was calculated using the following formula:
wherein k is 1,2,3, …, U, j is 1,2,3, …, m × n; mu.sjRepresents the average value of the j-th column element in the matrix a.
And subtracting the average value of the column of each element in the matrix A to obtain the matrix after the decentralization treatment.
S22, establishing a covariance matrix C for the matrix after the decentralization treatment, wherein the covariance matrix C can be in the form of:
where cov denotes the covariance function,
in the formula, biColumn vectors representing the ith column of the de-centered matrix, bjA column vector representing the j-th column of the de-centered matrix.
S23, calculating all eigenvalues lambda of the covariance matrix C1,λ2,…,λm*nAnd feature vectors p corresponding to the respective feature values1,p2,…,pm*n。
It will be appreciated that since the covariance matrix C is an m x n order square matrix, the covariance matrix C has m x n sets of eigenvalues and eigenvectors.
And S24, sequencing the m-n eigenvalues, selecting the largest h eigenvalues, forming a new eigenvector array Lambda according to the descending order, and forming a new eigenvector matrix P by eigenvectors corresponding to each eigenvalue in the eigenvector array Lambda.
Wherein, the feature array Λ may be:
Λ＝[λ1,λ2,…,λh]。
the feature vector matrix P may be:
s25, calculating the projection of the matrix after the decentration process on the eigenvector matrix P to obtain an eigenvector D of the eigenface, that is:
D＝A×P
in the formula, x represents matrix multiplication, and the eigenface main vector D represents a matrix of U rows and h columns; the form of the eigenface principal vector D may be:
and S3, acquiring the facial features of the user.
In order to ensure that the captured face image is an image of the user himself/herself, the operation performed by the user himself/herself is confirmed by biometric authentication before image capturing of the facial features of the user is performed.
Specifically, the living body authentication method adopts the existing face recognition technology, and verifies whether the user is a real living body operation by detecting the combined actions of blinking, opening the mouth, shaking the head or nodding the head of the user.
S4, establishing an association degree vector of the user facial feature image according to the user facial feature image and the feature face main vector, wherein the specific process is as follows:
and S41, converting the facial feature image of the user into a gray image. The size of the gray scale image is m × n pixels.
S42, converting the matrix of m × n pixels of the gray-scale image into m × n-dimensional row vector z.
S43, calculating the projection of the m × n row vector z on the eigenvector matrix P to obtain the eigenvector y of the eigenface of the user, that is:
y＝z×P
where x represents a matrix multiplication, and the eigenface principal vector y of the user represents a row vector of 1 row and h columns.
S44, calculating the relevance vector x of the facial feature image of the user, namely:
x＝(DDT)-1DyT，
in the formula, T represents a transpose of a matrix.
The relevance vector x represents a column vector of U rows and 1 columns, which may be of the form:
s5, generating a private key corresponding to the facial feature information of the user according to the relevance vector x, wherein the specific process is as follows:
s51, calculating the rounded integer e of each element in the relevance vector xgSpecifically, the following formula can be adopted:
eg＝round(xg·10τ),g＝1,2,…,U，
in the formula, round represents rounding according to a rounding rule; τ represents an adjustable parameter, which is a non-negative integer and can take the value of 1,2, … ….
And S52, arranging and generating a private key corresponding to the facial feature information of the user according to a preset sequence.
Specifically, when x ═ 1.25, 10.05, 0.03, …, 3.54]TWhen T denotes the transposition of the matrix and τ is 1, the private key corresponding to the generated user facial feature information is:
131000……35。
the private key generation method generates the private key based on the strong authentication biological characteristic information, the private key is strong in correlation with the facial characteristic information of the user, the safety of the private key can be improved, and the private key cannot be easily deduced to be a specific value.
Example two
As shown in fig. 2, on the basis of the above private key generation method, the present application also provides a private key generation system for a blockchain e-wallet based on facial features, which includes a recognition library establishing module 1, an extracting module 2, an image collecting module 3, an association degree vector establishing module 4, and a generating module 5.
The recognition library establishing module 1 is used for establishing a characteristic face recognition library according to a plurality of randomly acquired different face images.
The extraction module 2 is used for extracting the characteristic face principal vector from the gray level image corresponding to the face image in the characteristic face recognition library.
The image acquisition module 3 is used for acquiring facial feature images of users.
The relevance vector establishing module 4 is used for establishing relevance vectors of the facial feature images of the users according to the facial feature images of the users and the feature face main vectors.
The generating module 5 is configured to generate a private key corresponding to the facial feature information of the user according to the relevance vector.
Specifically, the identification library establishing module 1 includes a random acquisition module, a gray scale conversion module and a matrix establishing module. The random acquisition module is used for randomly acquiring U different face images. The gray level conversion module is used for converting U different face images into gray level images, and the size of each gray level image is represented by m × n pixels. The matrix construction module is used for forming a matrix A with U rows and m x n columns by the pixels of the gray level images corresponding to the U different face images.
Specifically, the extraction module 2 comprises a decentralized module, a covariance matrix establishing module, an eigenvalue and eigenvector calculation module, an eigenvector matrix establishing module and an eigenface principal vector calculation module.
The de-centering module subtracts the average value of the column where each element is located from each element in the matrix A to obtain the de-centered matrix. The covariance matrix building module builds a covariance matrix by calculating the covariance between column vectors in the matrix after the decentralization processing. The eigenvalue and eigenvector calculation module is used for calculating all eigenvalues of the covariance matrix and corresponding eigenvectors thereof. And the eigenvector matrix construction module forms an eigenvector matrix by utilizing eigenvectors corresponding to the largest multiple eigenvalues in sequence in all eigenvalues of the covariance matrix.
The characteristic face principal vector calculation module obtains the characteristic face principal vector by calculating the projection of the matrix subjected to the centralization treatment on the characteristic vector matrix.
Specifically, the relevancy vector establishing module 4 includes a matrix transformation module and a relevancy vector calculation module. The matrix transformation module is used for transforming a matrix formed by m-n pixels of the gray-scale image transformed by the facial feature image of the user into m-n dimensional row vectors. And the relevance vector calculation module calculates the relevance vector of the user facial feature image by using the projection of the m-n dimensional row vector on the feature vector matrix and the feature face main vector.
Specifically, the generation module 5 includes a rounding module and a ranking generation module. And the rounding module is used for calculating a rounded integer of each element in the relevance vector. The sequencing generation module is used for arranging and generating a private key corresponding to the facial feature information of the user according to a preset sequence.
It should be noted that: the private key generation system provided in the foregoing embodiment is only illustrated by dividing each program module, and in practical applications, the processing distribution may be completed by different program modules according to needs, that is, the internal structure of the private key generation system is divided into different program modules, so as to complete all or part of the processing described above. In addition, the private key generation system and the private key generation method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.
The private key generation system generates the private key based on the strong authentication biological characteristic information, the private key is strong in correlation with the facial characteristic information of the user, the safety of the private key can be improved, and the private key cannot be easily deduced to be a specific value.
Based on the hardware implementation of each module in the private key generation system, in order to implement the private key generation method provided in the embodiment of the present application, an embodiment of the present application further provides a private key generation apparatus for a blockchain electronic wallet based on facial features, which includes: a processor and a memory for storing a computer program capable of running on the processor. Wherein the processor, when executing the computer program, performs the steps of:
establishing a characteristic face recognition library;
extracting characteristic face principal vectors from gray level images corresponding to a plurality of face images in a characteristic face recognition library;
acquiring an image of facial features of a user;
establishing an association degree vector of the facial feature image of the user according to the facial feature image of the user and the feature face main vector;
and generating a private key corresponding to the facial feature information of the user according to the relevance vector.
In an exemplary embodiment, the present application further provides a computer storage medium, which is a computer readable storage medium, for example, a memory including a computer program, which is executable by a processor in a private key generation system to perform the steps in the private key generation method. The computer-readable storage medium may be a magnetic random access Memory (FRAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical disk, or a Compact Disc Read-Only Memory (CD-ROM), among other memories.
EXAMPLE III
As shown in fig. 3, the present application also provides a block chain-based personal electronic wallet, which includes a private key generated by any one of the private key generation methods described above, and the private key generation method is stored as an intelligent contract on the block chain. When a user needs to obtain the private key, the private key corresponding to the facial features of the user can be regenerated by using the private key generation method only by calling the intelligent contract from the block chain.
By adopting the private key generation method of the blockchain electronic wallet based on the facial features, the private key does not need to be recorded, and the risks of embezzlement and illegal use can be avoided. The method can enhance the decentralized nature of blockchain personal electronic wallets. The storage medium is not needed, and the private key can be reproduced according to the facial feature information of the user when the private key is lost or the storage device is forgotten to be carried. In addition, the private key generation method based on the strong authentication biological characteristics can effectively improve the safety of the private key, so that the private key cannot be easily deduced to be a specific value.
The foregoing is merely an illustrative embodiment of the present application, and any equivalent changes and modifications made by those skilled in the art without departing from the spirit and principles of the present application shall fall within the protection scope of the present application.
Claims (9)
1. A private key generation method of a blockchain electronic wallet based on facial features is characterized by comprising the following steps:
establishing a characteristic face recognition library;
extracting characteristic face principal vectors from gray level images corresponding to a plurality of face images in a characteristic face recognition library;
acquiring images of facial features of a user, and obtaining a characteristic face principal vector of the user by using the facial feature images of the user;
establishing an association degree vector of a user facial feature image according to the feature face main vector of the user and the extracted feature face main vector, wherein the specific process comprises the following steps:
converting a facial feature image of a user into a grayscale image, wherein the grayscale image has m × n pixels;
converting a matrix formed by m × n pixels of the gray-scale image into m × n dimensional row vectors z;
calculating the projection of the m x n dimensional row vector z on the feature vector matrix P to obtain the feature face main vector y of the user:
y＝z×P，
in the formula, x represents matrix multiplication, and the eigenface main vector y of the user represents a row vector of 1 row and h columns;
calculating an association degree vector x of the facial feature image of the user:
x＝(DDT)-1DyT，
in the formula, T represents the transposition of a matrix, and D represents a characteristic face principal vector;
and generating a private key corresponding to the facial feature information of the user according to the relevance vector.
2. The private key generation method according to claim 1, wherein the specific process of establishing the characteristic face recognition library in the step is as follows:
randomly collecting U different face images;
for each face image, correspondingly converting the face image into a gray image, wherein the size of the gray image is m × n pixels;
converting a matrix formed by m × n pixels of the gray-scale image into m × n dimensional row vectors;
and arranging the row vectors corresponding to the U different face images into a matrix A, wherein the matrix A is a matrix with U rows and m × n columns.
3. The private key generation method according to claim 2, wherein the specific process of extracting the eigenface principal vector in the step is as follows:
performing decentralized processing on each row of elements in the matrix A respectively;
establishing a covariance matrix for the matrix subjected to the decentralized processing;
calculating all eigenvalues of the covariance matrix and eigenvectors corresponding to the eigenvalues;
sorting the m-n characteristic values, selecting a plurality of largest characteristic values, forming a new characteristic array according to the sequence from large to small, and forming a new characteristic vector matrix by the characteristic vectors corresponding to the characteristic values in the characteristic array;
and calculating the projection of the matrix subjected to the centralization treatment on the characteristic vector matrix to obtain the characteristic face main vector.
4. The method for generating a private key according to claim 3, wherein the step of performing the decentralized processing on each column of elements in the matrix A respectively comprises:
calculating the average value of each column of elements;
in the formula (I), the compound is shown in the specification,
μjrepresents the average value of j column element in matrix A;
and subtracting the average value of the column of each element in the matrix A to obtain the matrix after the decentralization treatment.
5. The method for generating the private key according to claim 1, wherein the specific process of generating the private key corresponding to the facial feature information of the user according to the relevance vector in the step is as follows:
for each element in the relevance vector x, its rounded integer e is calculatedg：
eg＝round(xg·10τ),g＝1,2,L,U，
In the formula, round represents rounding according to a rounding rule; τ represents a tunable parameter, which is a non-negative integer;
and arranging and generating a private key corresponding to the facial feature information of the user according to a preset sequence.
6. The private key generation method according to any one of claims 1 to 5, wherein before the step of image-capturing the facial features of the user, the method further comprises the steps of: the user himself/herself is confirmed by a biometric authentication method.
7. A private key generation system for a blockchain wallet based on facial features, comprising:
the recognition base establishing module is used for establishing a characteristic face recognition base according to a plurality of randomly collected different face images;
the extraction module is used for extracting a characteristic face principal vector from a gray level image corresponding to a face image in a characteristic face recognition library;
the image acquisition module is used for acquiring facial feature images of users and obtaining feature face principal vectors of the users by utilizing the facial feature images of the users;
the relevancy vector establishing module is used for establishing relevancy vectors of the facial feature images of the users according to the feature face main vectors of the users and the extracted feature face main vectors; the relevancy vector establishing module comprises:
a matrix transformation module for transforming a matrix formed by m × n pixels of the gray-scale image transformed from the facial feature image of the user into m × n dimensional row vectors;
the relevance vector calculation module calculates the relevance vector of the user face feature image by using the projection of the m-n dimensional row vector on the feature vector matrix and the feature face main vector, and the process is as follows:
calculating the projection of the m x n dimensional row vector z on the feature vector matrix P to obtain the feature face main vector y of the user, namely:
y＝z×P；
in the formula, x represents matrix multiplication, and the eigenface main vector y of the user represents a row vector of 1 row and h columns;
calculating an association degree vector x of the facial feature image of the user, namely:
x＝(DDT)-1DyT，
in the formula, T represents a transposition of a matrix; d represents a characteristic face principal vector;
and the generating module is used for generating a private key corresponding to the facial feature information of the user according to the relevance vector.
8. A private key generation apparatus for a blockchain wallet based on facial features, comprising:
a processor for processing the received data, wherein the processor is used for processing the received data,
the processor is capable of invoking intelligent contracts from a blockchain,
the intelligent contract comprises a computer program that,
the computer program, when running on the processor, performs the steps of:
establishing a characteristic face recognition library;
extracting characteristic face principal vectors from gray level images corresponding to a plurality of face images in a characteristic face recognition library;
acquiring images of facial features of a user, and obtaining a characteristic face principal vector of the user by using the facial feature images of the user;
establishing an association degree vector of a user facial feature image according to the feature face principal vector of the user and the extracted feature face principal vector, wherein the specific process comprises the following steps:
converting a facial feature image of a user into a grayscale image, wherein the grayscale image has m × n pixels;
converting a matrix formed by m × n pixels of the gray-scale image into m × n dimensional row vectors z;
calculating the projection of the m x n dimensional row vector z on the feature vector matrix P to obtain the feature face main vector y of the user:
y＝z×P，
in the formula, x represents matrix multiplication, and the eigenface main vector y of the user represents a row vector of 1 row and h columns;
calculating an association degree vector x of the facial feature image of the user:
x＝(DDT)-1DyT，
in the formula, T represents the transposition of a matrix, and D represents a characteristic face principal vector;
and generating a private key corresponding to the facial feature information of the user according to the relevance vector.
9. A blockchain-based personal electronic wallet comprising a private key generated by the private key generation method of any one of claims 1 to 6, the private key generation method being stored as a smart contract on a blockchain.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910066500.8A CN109801072B (en) | 2019-01-24 | 2019-01-24 | Private key generation method and system of block chain electronic wallet based on facial features |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910066500.8A CN109801072B (en) | 2019-01-24 | 2019-01-24 | Private key generation method and system of block chain electronic wallet based on facial features |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109801072A CN109801072A (en) | 2019-05-24 |
| CN109801072B true CN109801072B (en) | 2021-08-27 |
Family
ID=66560159
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910066500.8A Active CN109801072B (en) | 2019-01-24 | 2019-01-24 | Private key generation method and system of block chain electronic wallet based on facial features |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109801072B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650370A (en) * | 2016-11-22 | 2017-05-10 | 西北工业大学 | Non-contact encryption method and system for computer |
| US9871783B2 (en) * | 2015-06-26 | 2018-01-16 | Verizon Patent And Licensing Inc. | Universal enrollment using biometric PKI |
| CN107644219A (en) * | 2017-10-10 | 2018-01-30 | 广东欧珀移动通信有限公司 | Face registration method and related product |
| CN108683646A (en) * | 2018-04-28 | 2018-10-19 | 厦门美图之家科技有限公司 | A kind of authentication method and computing device |
| CN108847931A (en) * | 2018-06-25 | 2018-11-20 | 北京奇虎科技有限公司 | Block chain key generation method and device based on biometric |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388888B (en) * | 2018-03-23 | 2022-04-05 | 腾讯科技（深圳）有限公司 | Vehicle identification method and device and storage medium |
-
2019
- 2019-01-24 CN CN201910066500.8A patent/CN109801072B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9871783B2 (en) * | 2015-06-26 | 2018-01-16 | Verizon Patent And Licensing Inc. | Universal enrollment using biometric PKI |
| CN106650370A (en) * | 2016-11-22 | 2017-05-10 | 西北工业大学 | Non-contact encryption method and system for computer |
| CN107644219A (en) * | 2017-10-10 | 2018-01-30 | 广东欧珀移动通信有限公司 | Face registration method and related product |
| CN108683646A (en) * | 2018-04-28 | 2018-10-19 | 厦门美图之家科技有限公司 | A kind of authentication method and computing device |
| CN108847931A (en) * | 2018-06-25 | 2018-11-20 | 北京奇虎科技有限公司 | Block chain key generation method and device based on biometric |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109801072A (en) | 2019-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Manisha et al. | Cancelable biometrics: a comprehensive survey | |
| Galbally et al. | Iris image reconstruction from binary templates: An efficient probabilistic approach based on genetic algorithms | |
| US9813909B2 (en) | Cloud server for authenticating the identity of a handset user | |
| Kuehlkamp et al. | Ensemble of multi-view learning classifiers for cross-domain iris presentation attack detection | |
| Zhang et al. | Touch gesture-based active user authentication using dictionaries | |
| Maiorana et al. | Cancelable templates for sequence-based biometrics with application to on-line signature recognition | |
| Ouda et al. | Bioencoding: A reliable tokenless cancelable biometrics scheme for protecting iriscodes | |
| TWI727329B (en) | Anti-spoofing system and method for providing selective access to resources based on a deep learning method | |
| CN110955874A (en) | Identity authentication method, identity authentication device, computer equipment and storage medium | |
| Bala et al. | Multimodal biometric system based on fusion techniques: a review | |
| Juefei-Xu et al. | Weight-optimal local binary patterns | |
| CA3049042A1 (en) | System and method for authenticating transactions from a mobile device | |
| Kar et al. | A multi-algorithmic face recognition system | |
| CN108875335B (en) | Method for unlocking human face and inputting expression and expression action, authentication equipment and nonvolatile storage medium | |
| Habibu et al. | Assessment of vulnerabilities of the biometric template protection mechanism | |
| Evangelin et al. | Securing recognized multimodal biometric images using cryptographic model | |
| CN109801072B (en) | Private key generation method and system of block chain electronic wallet based on facial features | |
| CN109977807B (en) | Face feature template protection method and system based on complex matrix | |
| Nazari et al. | Cancelable face using chaos permutation | |
| CN106971157B (en) | Identity coupling identification method based on multiple linear regression association memory model | |
| Fierrez et al. | Biometrics security | |
| CN109840487B (en) | Private key generation method and system of block chain electronic wallet based on fingerprint information | |
| KR100797897B1 (en) | Cerification system using optimal transform function of biometric data | |
| Patil et al. | Enhancement of feature extraction in image quality | |
| Fakhar et al. | Fusion of face and iris features extraction based on steerable pyramid representation for multimodal biometrics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |